Intent Segmentation of User Queries Via Discourse Parsing

Vicente Ivan Sanchez Carmona, Yibing Yang, Ziyue Wen, Ruosen Li, Xiaohua Wang, Changjian Hu


Abstract
In this paper, we explore a new approach based on discourse analysis for the task of intent segmentation. Our target texts are user queries from a real-world chatbot. Our results show the feasibility of our approach with an F1-score of 82.97 points, and some advantages and disadvantages compared to two machine learning baselines: BERT and LSTM+CRF.
Anthology ID:
2020.iwdp-1.7
Volume:
Proceedings of the Second International Workshop of Discourse Processing
Month:
December
Year:
2020
Address:
Suzhou, China
Editors:
Qun Liu, Deyi Xiong, Shili Ge, Xiaojun Zhang
Venue:
iwdp
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
38–47
Language:
URL:
https://preview.aclanthology.org/build-pipeline-with-new-library/2020.iwdp-1.7/
DOI:
10.18653/v1/2020.iwdp-1.7
Bibkey:
Cite (ACL):
Vicente Ivan Sanchez Carmona, Yibing Yang, Ziyue Wen, Ruosen Li, Xiaohua Wang, and Changjian Hu. 2020. Intent Segmentation of User Queries Via Discourse Parsing. In Proceedings of the Second International Workshop of Discourse Processing, pages 38–47, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
Intent Segmentation of User Queries Via Discourse Parsing (Sanchez Carmona et al., iwdp 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/build-pipeline-with-new-library/2020.iwdp-1.7.pdf